[PATCH v6 06/15] virtio-blk: check the write granularity of writes to sequential zones

[Niklas Cassel <cassel@kernel.org>]

All VIRTIO_BLK_T_OUT requests issued to sequential zones and all
VIRTIO_BLK_T_ZONE_APPEND requests must have an offset and a data size
that are multiples of the write granularity reported by the device
(virtio 1.4, 5.2.6.1), and a violation is reported as
VIRTIO_BLK_S_ZONE_UNALIGNED_WP (virtio 1.4, 5.2.6).

Neither request type was fully checked. Zone appends validated only the
offset, while writes were not checked at all.

Check the size of the appended data, and both the offset and the size of
a write, against blkconf_zone_write_granularity(), so that every request the
device accepts is one that the guest driver was told is valid. Writes to
conventional zones keep no alignment constraint beyond the logical block
size. The write path performs the check after virtio_blk_sect_range_ok()
so that the zone index derived from the guest supplied sector is known to
be in range.

Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 hw/block/virtio-blk.c | 38 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 37 insertions(+), 1 deletion(-)

diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 6bf1049aea..449de307b4 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -392,6 +392,33 @@ static bool virtio_blk_sect_range_ok(VirtIOBlock *dev,
     return true;
 }
 
+/*
+ * Both the offset and the size of a write to a sequential zone must be a
+ * multiple of the write granularity that the device reports. Conventional
+ * zones are not constrained. The zone index is derived from a guest supplied
+ * sector, so this must only be called once virtio_blk_sect_range_ok() has
+ * bounded it.
+ */
+static bool virtio_blk_zone_write_granularity_ok(VirtIOBlock *dev,
+                                                 uint64_t sector, size_t size)
+{
+    BlockDriverState *bs = blk_bs(dev->blk);
+    uint64_t offset = sector << BDRV_SECTOR_BITS;
+    uint32_t wg_mask;
+
+    if (bs->bl.zoned == BLK_Z_NONE) {
+        return true;
+    }
+
+    if (bdrv_zone_is_conv(bs, bdrv_zone_index(bs, offset))) {
+        return true;
+    }
+
+    wg_mask = blkconf_zone_write_granularity(&dev->conf.conf) - 1;
+
+    return !(offset & wg_mask) && !(size & wg_mask);
+}
+
 static uint8_t virtio_blk_handle_discard_write_zeroes(VirtIOBlockReq *req,
     struct virtio_blk_discard_write_zeroes *dwz_hdr, bool is_write_zeroes)
 {
@@ -518,7 +545,7 @@ static bool check_zoned_request(VirtIOBlock *s, int64_t offset, int64_t len,
     if (append) {
         uint32_t wg_mask = blkconf_zone_write_granularity(&s->conf.conf) - 1;
 
-        if (offset & wg_mask) {
+        if (offset & wg_mask || len & wg_mask) {
             *status = VIRTIO_BLK_S_ZONE_UNALIGNED_WP;
             return false;
         }
@@ -913,6 +940,15 @@ static int virtio_blk_handle_request(VirtIOBlockReq *req, MultiReqBuffer *mrb)
             return 0;
         }
 
+        if (is_write &&
+            !virtio_blk_zone_write_granularity_ok(s, req->sector_num,
+                                                  req->qiov.size)) {
+            virtio_blk_req_complete(req, VIRTIO_BLK_S_ZONE_UNALIGNED_WP);
+            block_acct_invalid(blk_get_stats(s->blk), BLOCK_ACCT_WRITE);
+            g_free(req);
+            return 0;
+        }
+
         block_acct_start(blk_get_stats(s->blk), &req->acct, req->qiov.size,
                          is_write ? BLOCK_ACCT_WRITE : BLOCK_ACCT_READ);
 
-- 
2.55.0